Research map / Architectures and efficiency / Spiking networks
Pseudo-Spiking Neurons: A Noise-Based Training Framework for Heterogeneous-Latency Spiking Neural Networks
Yuxuan Zhang, Yuhang Sun, Hongjue Li, Yue Deng, Wen Yao
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| learn heterogeneous per-layer timesteps with noise proxy instead of fixed timestep | SNN ResNet-19 · CIFAR-100 | top-1 accuracy: 80.71 -> 81.29 vs RateBP at ~3 avg timesteps (MTT 81.51 at T=4) | Mixed |
| learned heterogeneous latency vs RateBP on ImageNet | SEW-ResNet-34 · ImageNet | top-1 accuracy: 65.84 -> 68.18 | Improved |
| add both quantization and clipping noise (vs single term) (ablation) | PseudoSNN ResNet-18 · CIFAR-100 | top-1 accuracy: 31.16 -> 79.02 (clipping only vs full, no calibration) | Improved |
| add 10-epoch calibration fine-tuning (ablation) | PseudoSNN ResNet-18 · CIFAR-100 | top-1 accuracy: 79.02 -> 79.57 | Improved |
| use PseudoSN proxy vs BPTT/RateBP for training | ResNet-18 · CIFAR-100 training cost | training time and memory | Improved |
| learned heterogeneous timesteps vs uniform timestep SEW-ResNet-34 | SEW-ResNet-34 · ImageNet | energy (mJ): 4.89 -> 4.13 mJ | Improved |
| vary lambda in hardware-aware penalty (ablation) | PseudoSNN ResNet-18 · CIFAR-100 | accuracy-latency Pareto | Improved |
Closest papers by meaning
- Enhancing Training of Spiking Neural Network with Stochastic Latency (AAAI 2024 · similarity 0.93)
- Temporal Flexibility in Spiking Neural Networks: Towards Generalization Across Time Steps and Deployment Friendliness (ICLR 2025 · similarity 0.91)
- Advancing Training Efficiency of Deep Spiking Neural Networks through Rate-based Backpropagation (NeurIPS 2024 · similarity 0.90)
- SpikingSSMs: Learning Long Sequences with Sparse and Parallel Spiking State Space Models (AAAI 2025 · similarity 0.90)
- Efficient Parallel Training Methods for Spiking Neural Networks with Constant Time Complexity (ICML 2025 · similarity 0.90)
- NDOT: Neuronal Dynamics-based Online Training for Spiking Neural Networks (ICML 2024 · similarity 0.90)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
